Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74090
    Prev
    Next
    INDEX
    Explanations

    "finish"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.94
    Espèce
    -0.90
    SharedCtor
    -0.79
     EconPapers
    -0.78
     Normdatei
    -0.74
    جغرافيا
    -0.72
     SEDS
    -0.72
    IUrlHelper
    -0.71
    ✨:
    -0.69
    tanleria
    -0.69
    POSITIVE LOGITS
     finish
    0.57
     are
    0.55
     fin
    0.44
    finish
    0.44
    fin
    0.43
    gridx
    0.42
    <bos>
    0.41
    ¿
    0.39
     am
    0.39
     FINISH
    0.37
    Activations Density 0.000%

    No Known Activations